American Research Group, Inc.

 

2020 Iowa Presidential Election Pollster Ratings

 

The following table lists the preliminary accuracy of pollsters in the November 3, 2020 Iowa presidential election using the measure of polling accuracy proposed by Martin, Traugott, and Kennedy.

An accuracy measure of 0.00 indicates that the odds ratio of the survey results matches the odds ratio of the actual results (the closer to 0.00, the better).

 

2020 Iowa President
Biden Trump Odds
Ratio
Accuracy
Des Moines Register 41% 48% 1.01 0.01 
Insider Advantage 46% 48% 1.13 0.12 
Emerson 46% 47% 1.16 0.15 
Quinnipac 46% 47% 1.16 0.15*
CBS News/YouGov 49% 49% 1.18 0.17*
PPP 49% 48% 1.21 0.19*
NYT/Siena 46% 43% 1.26 0.23*
Monmouth 50% 47% 1.26 0.23*
WHO-TV13 50% 46% 1.29 0.25*
Actual 45.0% 53.2%

 

*The accuracy measures for the Quinnipac poll (sample size of 1,225), the CBS News/YouGov poll (sample size of 1,035), the PPP poll (sample size of 871), the New York Times/Siena poll (sample size of 753), the Monmouth poll (sample size of 501), and the WHO-TV13 poll (sample size of 693) fall outside the 95% confidence intervals. This represents approximately 67% of all final polls in Iowa. 

The accuracy measures for the other 3 polls fall within the 95% confidence intervals.

The average absolute accuracy for all polls is 0.166.

The average absolute accuracy for the 3 polls where the accuracy measures fall within the respective 95% confidence intervals is 0.093.

In 2016 in Iowa, the average absolute accuracy for 8 final polls was 0.134. Of the 8 final polls, 5 had accuracy measures that were within the respective 95% confidence intervals.

As a reference: The average absolute accuracy for all polls in the 2016 presidential election was 0.070. The average absolute accuracy for all polls in the 2012 presidential election was 0.055. The average absolute accuracy for all polls in the 2008 presidential election was 0.037.

ARG Home